Neural Implicit Surface Evolution using Differential Equations.

Abstract: In this talk, we present a machine learning framework that uses smooth neural networks to model dynamic variations of implicit surfaces under partial differential equations.

Examples include evolving an initial surface towards vector fields, smoothing and sharpening using the mean curvature equation, and interpolations of implicit surfaces regularized by specific differential equations.

Posted on Dec 16, 2022 in Differential Equations, Seminars